| { | |
| "best_metric": 0.4981158375740051, | |
| "best_model_checkpoint": "output_pipe/H3K9ac/origin/checkpoint-600", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 1392, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28735632183908044, | |
| "grad_norm": 14.2805814743042, | |
| "learning_rate": 2.897168405365127e-05, | |
| "loss": 0.6236, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5747126436781609, | |
| "grad_norm": 21.02322769165039, | |
| "learning_rate": 2.6736214605067064e-05, | |
| "loss": 0.558, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5747126436781609, | |
| "eval_accuracy": 0.7207628643396905, | |
| "eval_f1": 0.7207078582418551, | |
| "eval_loss": 0.5503345131874084, | |
| "eval_matthews_correlation": 0.45773632763109845, | |
| "eval_precision": 0.7295566235835433, | |
| "eval_recall": 0.7281817687967431, | |
| "eval_runtime": 1.2556, | |
| "eval_samples_per_second": 2213.338, | |
| "eval_steps_per_second": 35.044, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 7.396298885345459, | |
| "learning_rate": 2.450074515648286e-05, | |
| "loss": 0.5634, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "grad_norm": 32.200721740722656, | |
| "learning_rate": 2.2265275707898658e-05, | |
| "loss": 0.4479, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "eval_accuracy": 0.7387549478229579, | |
| "eval_f1": 0.7364658766732499, | |
| "eval_loss": 0.5588128566741943, | |
| "eval_matthews_correlation": 0.4729348489978345, | |
| "eval_precision": 0.7365314322327897, | |
| "eval_recall": 0.7364034340861676, | |
| "eval_runtime": 1.2575, | |
| "eval_samples_per_second": 2209.978, | |
| "eval_steps_per_second": 34.991, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.4367816091954024, | |
| "grad_norm": 9.86948013305664, | |
| "learning_rate": 2.0029806259314457e-05, | |
| "loss": 0.4225, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 10.367095947265625, | |
| "learning_rate": 1.7794336810730255e-05, | |
| "loss": 0.3986, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "eval_accuracy": 0.7711406980928391, | |
| "eval_f1": 0.7698885118456165, | |
| "eval_loss": 0.4981158375740051, | |
| "eval_matthews_correlation": 0.5402802887183997, | |
| "eval_precision": 0.769419869237036, | |
| "eval_recall": 0.7708623450863797, | |
| "eval_runtime": 1.2625, | |
| "eval_samples_per_second": 2201.194, | |
| "eval_steps_per_second": 34.852, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.0114942528735633, | |
| "grad_norm": 22.41069984436035, | |
| "learning_rate": 1.555886736214605e-05, | |
| "loss": 0.3899, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "grad_norm": 13.146961212158203, | |
| "learning_rate": 1.332339791356185e-05, | |
| "loss": 0.2213, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "eval_accuracy": 0.7682619647355163, | |
| "eval_f1": 0.763870065442263, | |
| "eval_loss": 0.5538982152938843, | |
| "eval_matthews_correlation": 0.5308867641648468, | |
| "eval_precision": 0.7687626709677005, | |
| "eval_recall": 0.7621650872781482, | |
| "eval_runtime": 1.2613, | |
| "eval_samples_per_second": 2203.29, | |
| "eval_steps_per_second": 34.885, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.586206896551724, | |
| "grad_norm": 15.811505317687988, | |
| "learning_rate": 1.1087928464977646e-05, | |
| "loss": 0.2116, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.873563218390805, | |
| "grad_norm": 23.64767837524414, | |
| "learning_rate": 8.852459016393443e-06, | |
| "loss": 0.2063, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.873563218390805, | |
| "eval_accuracy": 0.7894926232457719, | |
| "eval_f1": 0.7876337270113377, | |
| "eval_loss": 0.5589863657951355, | |
| "eval_matthews_correlation": 0.5752726316278426, | |
| "eval_precision": 0.7877340245479454, | |
| "eval_recall": 0.7875386402598339, | |
| "eval_runtime": 1.2583, | |
| "eval_samples_per_second": 2208.486, | |
| "eval_steps_per_second": 34.967, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.160919540229885, | |
| "grad_norm": 23.754074096679688, | |
| "learning_rate": 6.61698956780924e-06, | |
| "loss": 0.1208, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "grad_norm": 7.369907379150391, | |
| "learning_rate": 4.381520119225037e-06, | |
| "loss": 0.0704, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "eval_accuracy": 0.7959697732997482, | |
| "eval_f1": 0.7935314533434963, | |
| "eval_loss": 0.8873270153999329, | |
| "eval_matthews_correlation": 0.5875264868648358, | |
| "eval_precision": 0.7948583351751866, | |
| "eval_recall": 0.7926722188153907, | |
| "eval_runtime": 1.2532, | |
| "eval_samples_per_second": 2217.534, | |
| "eval_steps_per_second": 35.11, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.735632183908046, | |
| "grad_norm": 36.424137115478516, | |
| "learning_rate": 2.1684053651266765e-06, | |
| "loss": 0.0653, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1392, | |
| "total_flos": 6947594995138560.0, | |
| "train_loss": 0.3127735472958663, | |
| "train_runtime": 137.0169, | |
| "train_samples_per_second": 648.796, | |
| "train_steps_per_second": 10.159 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1392, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6947594995138560.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |